© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 878
    Prev
    Next
    INDEX
    Explanations

    phrases related to logic and probability

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to scientific theory and hypothesis testing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cair
    -0.72
    anwhile
    -0.71
     Pork
    -0.71
     Parkway
    -0.71
    cigarette
    -0.71
     Sod
    -0.69
     flush
    -0.69
    horn
    -0.69
    ovember
    -0.68
    kiss
    -0.68
    POSITIVE LOGITS
     empirical
    1.59
     epist
    1.55
     hypotheses
    1.54
     normative
    1.49
     causal
    1.44
     methodological
    1.40
     empir
    1.38
     inference
    1.37
     presupp
    1.35
     explanatory
    1.33
    Activations Density 0.335%

    No Known Activations